Causal Inference Using Graphical Models with the<i>R</i>Package<b>pcalg</b>

Kalisch, Markus; Mächler, Martin; Colombo, Diego; Maathuis, Marloes H.; Bühlmann, Peter

doi:10.18637/jss.v047.i11

Cited by 482 publications

(399 citation statements)

References 17 publications

Supporting

Mentioning

381

Contrasting

Unclassified

Order By: Relevance

“…The CD algorithm is implemented in R with the majority of its core computation executed in C programs. The PC algorithm we used was implemented by Kalisch et al (2012) in the R package pcalg. The running time for the PC algorithm depends on the argument u2pd, which we assume to be rand (see online manuals for further details).…”

Section: Comparison With Other Methodsmentioning

confidence: 99%

Learning Sparse Causal Gaussian Networks With Experimental Intervention: Regularization and Coordinate Descent

Zhou

2013

Journal of the American Statistical Association

129

View full text Add to dashboard Cite

Causal networks are graphically represented by directed acyclic graphs (DAGs). Learning causal networks from data is a challenging problem due to the size of the space of DAGs, the acyclicity constraint placed on the graphical structures, and the presence of equivalence classes. In this article, we develop an L 1 -penalized likelihood approach to estimate the structure of causal Gaussian networks. A blockwise coordinate descent algorithm, which takes advantage of the acyclicity constraint, is proposed for seeking a local maximizer of the penalized likelihood. We establish that model selection consistency for causal Gaussian networks can be achieved with the adaptive lasso penalty and sufficient experimental interventions. Simulation and real data examples are used to demonstrate the effectiveness of our method. In particular, our method shows satisfactory performance for DAGs with 200 nodes, which have about 20,000 free parameters. Supplementary materials for this article are available online.

show abstract

Section: Comparison With Other Methodsmentioning

confidence: 99%

Learning Sparse Causal Gaussian Networks With Experimental Intervention: Regularization and Coordinate Descent

Zhou

2013

Journal of the American Statistical Association

129

View full text Add to dashboard Cite

show abstract

“…This is the only mandatory argument and can either be a weights matrix, an edge-list or an object of class "qgraph", "loadings" and "factanal" (stats; R Development Core Team 2012), "principal" (psych; Revelle 2012), "sem" and "semmod" (sem; Fox et al 2012), "lavaan" (lavaan; Rosseel 2012), "graphNEL" (Rgraphviz; Gentry et al 2012) or "pcAlgo" (pcalg; Kalisch et al 2012). In this article we focus mainly on weights matrices, information on other input modes can be found in the documentation.…”

Section: Input Modesmentioning

confidence: 99%

qgraph: Network Visualizations of Relationships in Psychometric Data

Epskamp¹,

Cramer²,

Waldorp³

et al. 2012

J. Stat. Soft.

3,412

2,445

View full text Add to dashboard Cite

We present the qgraph package for R, which provides an interface to visualize data through network modeling techniques. For instance, a correlation matrix can be represented as a network in which each variable is a node and each correlation an edge; by varying the width of the edges according to the magnitude of the correlation, the structure of the correlation matrix can be visualized. A wide variety of matrices that are used in statistics can be represented in this fashion, for example matrices that contain (implied) covariances, factor loadings, regression parameters and p values. qgraph can also be used as a psychometric tool, as it performs exploratory and confirmatory factor analysis, using sem and lavaan; the output of these packages is automatically visualized in qgraph, which may aid the interpretation of results. In this article, we introduce qgraph by applying the package functions to data from the NEO-PI-R, a widely used personality questionnaire.

show abstract

“…Undirected graphs will be used to visualize mutual association between functioning variables, whereas directed acyclic graphs will be used to represent the effect of hypothetical interventions in each functioning variable on people's health. The undirected graph, called a skeleton, will be estimated using the PC algorithm implemented by Kalisch et al 43 In this algorithm, a series of conditional independence tests (starting with three functioning variable and then increasing the set of functioning variables step by step) are carried out for eliminating the edges from a complete graph, that is, one within which all variables (nodes) are connected. The final edges in the skeleton indicate some strong dependence that cannot be explained by conditioning on other variables.…”

Section: Data Analysis Plan For the Lived Experience Across Countriesmentioning

confidence: 99%

Study Protocol of the International Spinal Cord Injury (InSCI) Community Survey

Gross-Hemmi

Post

Ehrmann

et al. 2017

American Journal of Physical Medicine &Amp; Rehabilitation

View full text Add to dashboard Cite

Objective: The Learning Health System for Spinal Cord Injury (LHS-SCI) is an initiative embedded in the World Health Organization's (WHO's)Global Disability Plan and requires the statistical collection of data on the lived experience of persons with SCI to consequently formulate recommendations and policies. The International Spinal Cord Injury (InSCI) community survey has been developed as an initial step to gain information about the lived experience of persons with SCI within and across diverse nations. Design: InSCI is a multinational community survey based on the International Classification of Functioning, Disability and Health Core Sets for SCI and involves 28 countries from all six WHO regions. The study will be implemented in 2017. Overall aims, guiding principles on sampling strategies, data collection modes, and reminder management are described. Conclusions: InSCI will be the first survey to be conducted simultaneously in many countries and in all six WHO world regions that identifies the factors associated with functioning, health, and well-being of persons living with SCI. Expected results of the survey will be used for the basis of conducting stakeholder dialogs for policy reforms designed to improve the functioning, health maintenance, and well-being of persons with SCI.

show abstract

Causal Inference Using Graphical Models with theRPackagepcalg

Cited by 482 publications

References 17 publications

Learning Sparse Causal Gaussian Networks With Experimental Intervention: Regularization and Coordinate Descent

Learning Sparse Causal Gaussian Networks With Experimental Intervention: Regularization and Coordinate Descent

qgraph: Network Visualizations of Relationships in Psychometric Data

Study Protocol of the International Spinal Cord Injury (InSCI) Community Survey

Contact Info

Product

Resources

About